Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer 事件

Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer arXiv:2601.05770v3 Announce Type: replace-cross Abstract: Algorithm extraction aims to synthesize executable programs directly from models trained on algorithmic tasks, enabling de novo recovery of executable mechanisms from weights without relying on human-written target programs. However, applying this paradigm to Transformer is complicated by representation entanglement (e.g., superposition), where features en